A method of partially optimal scaling is developed by incorporating a simple subjective scoring method into optimal scaling. The method mitigates practical problems of the data size and the a priori order of response categories. On the basis of Monte Carlo computations, some guidelines for differential use of partially optimal scaling, optimal scaling or the combination of the two are suggested.
No takes yet. Share an insight, caveat, or question.
Nishisato et al. (1972) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: